Search

The latest deep neural networks for medical segmentation typically utilize transposed convolutional filters and atrous convolutional filters for spatial restoration and larger receptive fields, leading to dilution and inconsistency of visual semantics. To address such issues, we propose a novel attentional up-concatenation structure to build an auxiliary path for direct access to multi-level features. In addition, we employ a new structural loss to bring better morphological awareness and reduce the segmentation flaws caused by the semantic inconsistencies. Thorough experiments on the challenging optic cup/disc segmentation, cellular segmentation and lung segmentation tasks were performed to evaluate the proposed methods. Further ablation analysis demonstrated the effectiveness of the different components of the model and illustrated its efficiency. The proposed methods achieved the best performance and speed compared to the state-of-the-art models in three tasks on seven public datasets, including DRISHTI-GS, RIM-r3, REFUGE, MESSIDOR, TNBC, GlaS and LUNA. • A deep learning model, Up-Net, is proposed to overcome semantic inconsistency issue. • A lightweight up-concatenation structure and metric learning strategy is proposed. • We validated Up-Net in 3 challenging medical segmentation tasks across 7 datasets. [ABSTRACT FROM AUTHOR]

Transfer learning from natural image datasets, such as ImageNet, is common for applying deep learning to medical imaging. However, the modalities of natural and medical images differ considerably, and the reason for the latest medical research preferring ImageNet to medical data is questionable. In this study, we investigated the properties of medical pre-training and its transfer effectiveness on various medical tasks. Through an intuitive convolution-based analysis, we determined the modality characteristics of images. Surprisingly, medical pre-training showed exceptional performance for a classification task but not for a segmentation task since medical data are visually homogeneous and lack morphological information. Using data with diverse modalities helped overcome such drawbacks, resulting in medical pre-training achieving performance comparable to pre-training with ImageNet with considerably fewer samples than ImageNet for both aforementioned tasks. Finally, a study of learned representations and realistic scenarios indicated that while ImageNet is the best choice for medical imaging, medical pre-training has significant potential. • We study the transfer learning effectiveness based on medical and natural images. • We evaluate medical pre-training on downstream medical image analysis tasks. • We reveal the shortcomings and future potential of medical pre-training. [ABSTRACT FROM AUTHOR]

AgNbO 3 semiconductor have attracted much attention due to its unique visible-light photosensitivity. The first-principles calculations were used to investigate the relationship among the structural evolution, electronic structure, optical properties and carrier lifetime of La doped Ag 1- x La x NbO 3. The addition of La enlarges the cell volume and inhibits the lattice distortion, which promotes the separation of photogenerated electron-hole pairs. After La doping, the La 4 d state gradually extends to the fermi level, resulting in more electrons to participate in the reduction reaction. The light absorption of Ag 1- x La x NbO 3 at visible range and the utilization capacity of sunlight are enhanced. The m e * of Ag 1- x La x NbO 3 is reduced, which is conducive to the charge transfer and guarantees the electronic mobility and carrier lifetime in the compound. Our study demonstrats that La doping can effectively improve the photocatalytic performance of AgNbO 3 , which provides a reference for the experimental research of photocatalytic water decomposition. [Display omitted] • The incorporation of La leads to the expanded lattice volume and the suppressed distortion, resulting in a stronger external electric field, which prevents the rapid recombination of carriers. • The band edge position for Ag 1- x La x NbO 3 shows that the incorporation of La can reduce the bandgap and enhance the electron reducibility in the system, so as to improve the photocatalytic capacity. • La doped AgNbO 3 facilitates the carrier migration and decreases the recombination rate of electron and hole, thus prolonging carrier lifetime and improving photocatalytic ability. • The absorption capacity of Ag 1- x La x NbO 3 in the light with 600∼900 nm wavelength is enhanced, which improves the photocatalytic performance of the material in the visible light range. [ABSTRACT FROM AUTHOR]

Nodular fasciitis is a benign, self-limited, pseudosarcomatous neoplasm that is cytogenetically characterized by recurrent USP6 gene rearrangement. Involvement of the breast by nodular fasciitis is very rare with only a few documented cases. It can clinically, radiologically and histologically mimic a malignancy, posing significant diagnostic challenges to clinicians, radiologists, and pathologists. In this study, we report 2 cases of nodular fasciitis occurring in the female breast, reviewing the literature and emphasizing the application of fluorescence in situ hybridization analysis of USP6 gene rearrangement in its diagnosis and differential diagnosis. [ABSTRACT FROM AUTHOR]

Surface water pollution has always posed a serious challenge to water quality management. Improving water quality management requires figuring out how to comprehend water quality conditions scientifically and effectively as well as quantitatively identify regional pollution sources. In this study, Xianghai Lake, a typical lake-type wetland on the Northeast China Plain, was taken as the research area. Based on a geographic information system (GIS) method and 11 water quality parameters, the single-factor evaluation and comprehensive water quality index (WQI) methods were used to comprehensively evaluate the water quality of the lake-type wetland in the level period. Four key water quality parameters were determined by the principal component analysis (PCA) method, and more convenient comprehensive water quality evaluation models, the minimum WQI considering weights (WQI min-w) and the minimum WQI without considering weights (WQI min-nw) were established. The multiple statistical method and the absolute principal component score-multiple liner regression (APCS-MLR) model were combined to analyse the lake pollution sources based on the spatial changes in pollutants. The findings demonstrated that the WQI min-nw model's water quality evaluation outcome was more accurate when weights were not taken into account. The WQI min-nw model can be used as a simple and convenient way to comprehend the variations in water quality in wetlands of lakes and reservoirs. It was concluded that the comprehensive water quality in the study area was at a "medium" level, and COD Mn was the main limiting factor. Nonpoint source pollution (such as agricultural planting and livestock breeding) was the most important factor affecting the water quality of Xianghai Lake (with a comprehensive contribution rate of 31.65%). The comprehensive contribution rates of sediment endogenous and geological sources, phytoplankton and other plants, and water diversion and other hydrodynamic impacts accounted for 25.12%, 19.65%, and 23.58% of the total impact, respectively. This study can provide a scientific method for water quality assessment and management of lake wetlands, and an effective support for migration of migratory birds, habitat protection and grain production security. [Display omitted] • We developed a WQI min model suitable for lake and reservoir type wetlands. • PCA/APCS-MLR is feasible for quantitative source analysis of lake and reservoir type wetlands. • Diversion works have dual impacts and scientifically designed diversion works are beneficial for improving water quality. • Endogenous/geological sources are important factors that cannot be ignored in water pollution. • Strengthening management of agricultural livestock and poultry breeding can better improve water quality. [ABSTRACT FROM AUTHOR]

Imidacloprid is a neonicotinoid that targets sucking pests, such as aphids and the green leaf bug and has been widely applied in wheat fields to control wheat aphids in China. To investigate the involvement of miRNAs in imidacloprid resistance, we sequenced small RNA libraries of Sitobion miscanthi Fabricius, across two different treatments using Illumina short-read sequencing technology. As a result, 265 microRNAs (miRNAs), of which 242 were known and 23 were novel, were identified. Quantitative analysis of miRNA levels showed that 23 miRNAs were significantly up-regulated, and 54 miRNAs were significantly down-regulated in the nymphs of S. miscanthi treated with imidacloprid in comparison with those of the control. Modulation of the abundances of differentially expressed miRNAs, smi-miR-316, smi-miR-1000, and smi-miR-iab-4 by the addition of the corresponding antagomir/inhibitor to the artificial diet significantly changed the susceptibility of S. miscanthi to imidacloprid. Subsequently, the post-transcriptional regulatory mechanism was conducted, smi-miR-278 and smi-miR-316 were confirmed to be participated in the post-transcriptional regulation of nAChRα1A and CYP4CJ6, respectively. The results suggested that miRNAs differentially expressed in response to imidacloprid could play a critical regulatory role in the metabolism of S. miscanthi to imidacloprid. [Display omitted] • 77 differentially expressed miRNAs identified under imidacloprid exposure using Illumina short-read sequencing technology. • Modulation abundances of smi-miR-316, smi-miR-1000 and smi-miR-iab-4 significantly changed the susceptibility to imidacloprid. • CYP4CJ6 and nAChRα1A could be regulated by smi-miR-316 and smi-miR-278, respectively. [ABSTRACT FROM AUTHOR]